Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1613 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0490. Min Range: -1.0490

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1134005 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1548513 (Python Code)

Max Activating Token Index: 107

Text #2

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.9584. Min Act: 0.0000

Data Index: 1446013 (Python Code)

Max Activating Token Index: 630

Text #3

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1411707 (Python Code)

Max Activating Token Index: 215

Text #4

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1567159 (Python Code)

Max Activating Token Index: 184

Text #5

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8771. Min Act: -0.0000

Data Index: 1401983 (Python Code)

Max Activating Token Index: 104

Text #6

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8525. Min Act: 0.0001

Data Index: 1387544 (Python Code)

Max Activating Token Index: 135

Text #7

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8674. Min Act: 0.0000

Data Index: 1489152 (Python Code)

Max Activating Token Index: 215

Text #8

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8446. Min Act: 0.0001

Data Index: 1604857 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8865. Min Act: 0.0001

Data Index: 1555789 (Python Code)

Max Activating Token Index: 157

Text #10

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8576. Min Act: -0.0000

Data Index: 759687 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8068. Min Act: 0.0000

Data Index: 1366839 (Python Code)

Max Activating Token Index: 413

Text #12

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7995. Min Act: -0.0000

Data Index: 614378 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1160253 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1468530 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1447815 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1531285 (Python Code)

Max Activating Token Index: 140

Text #17

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7419. Min Act: 0.0000

Data Index: 1510376 (Python Code)

Max Activating Token Index: 140

Text #18

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7824. Min Act: -0.0000

Data Index: 816296 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1416478 (Python Code)

Max Activating Token Index: 667